CivArchive
    Model trainer/creator: kblueleaf Uploaded to MoescapeA by Laanver Phi [Please view the full model detail on CivitAI] rev1 Source: https://civitai.com/models/399873?modelVersionId=445973 rev2 Source: https://civitai.com/models/399873?modelVersionId=546178 *Please check the [Usage1] and [Usage2] page to see how to use to checkpoint. Check [Models1] and [Models2] for understanding of the difference between versions. Check [Others] and for other details. Generally check the CivitAI page for complete breakdown. Kohaku' XL εpsilon: The best example of tuning t2i model at home with consumer-level hardware join us: https://discord.gg/tPBsKDyRR5 Introduction: Kohaku--- - XL Epsilon, the fifth major iteration in the Kohaku XL series, features a 5.2 million images dataset, LyCORIS fine-tuning[1], trained on comsumer-level hardware, and is fully open-sourced. Benchmark: *please check the CivitAI page for the graph. CCIP score on 3600 characters. (0~1, higher is better). Clearly, Kohaku XL Epsilon is way better than Kohaku XL Delta

    Description

    Tags: All the danbooru tags with at least 1000 popularity should work. All the danbooru tags with at least 100 popularity can possibly work with high emphasis. Remember to remove all the underscore in tags. (Underscores in short tags are not be removed, which are very likely part of emoji tags.) Remember to use 'xxx\(yyy\)' when tag have bracket and you are using sd-webui. Special Tags: - Quality tags: masterpiece, best quality, great quality, good quality, normal quality, low quality, worst quality - Rating tags: safe, sensitive, nsfw, explicit - Date tags: newest, recent, mid, early, old Quality Tags: Quality tags are assigned based on the percentile rankings of the favorite count (fav_count) within each rating category to avoid bias on nsfw content (Animagine XL v3 have met this problem), organized from high to low as follows: 90th, 75th, 60th, 45th, 30th, and 10th percentiles. This creates seven distinct quality levels separated by six thresholds. I lower the threshold since I found that the average quality of images in Danbooru is higher than I expected. Rating tags: - General: safe - Sensitive: sensitive - Questionable: nsfw - Explicit: nsfw, explicit Note: During training, content tagged as "explicit" is also considered under "nsfw" to ensure a comprehensive understanding. Date tags: Date tags are based on the upload dates of the images, as the metadata does not include the actual creation dates. The periods are categorized as follows: - 2005~2010: old - 2011~2014: early - 2015~2017: mid - 2018~2020: recent - 2021~2024: newest Resolution: This model is trained for resolutions from ARB 1024x1024 with minimum resolution 256 and maximum resolution 4096. This means you can use the standard SDXL resolution. However, opting for a slightly higher resolution than 1024x1024 is recommended. Applying a hires-fix is also suggested for better results. For more information, please check out the sample images provided.

    FAQ